Unverified50% confidenceBenchmarkExact time
The research tested 7 skills and 4 victim models.
1
Sources
50%
Confidence
Long-term
Relevance
9/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe research team selected 8 models spanning different capability tiers and conducted cross-evaluations across 54 benchmarks74% similarUnverifiedThe research team constructed a benchmark dataset containing 5,078 interpersonal conflict scenarios covering six ethical dimensions.69% similarUnverifiedThe tested task was conducted over four rounds, dispatching a cumulative total of 68 sub-agents to complete batch prompt testing for a digital human writing skills module.69% similarUnverified文章提出了8个测试人必备的Skill：需求文档转测试用例、Swagger接口文档转接口测试脚本、Bug报告生成器、测试日志智能分析、自动化脚本代码生成、测试报告摘要生成、代码Review助手、性能测试结果分析69% similarUnverifiedThis Skill has built-in auxiliary scripts for scanning, scoring, and failure analysis, used to grade existing selector strategies and identify high-risk fragile selectors.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/911413API
curl https://kongchang.com/api/v1/knowledge/claims/911413MCP
get_claim(id=911413)